Leveraging GPT-2 for Classifying Spam Reviews with Limited Labeled Data via Adversarial Training
This work is significant for e-commerce platforms and consumers, as it improves the accuracy of spam review detection, which is crucial for maintaining the integrity of online reviews, especially when labeled data is limited.
This paper addresses the challenge of classifying spam reviews with limited labeled data by proposing an adversarial training mechanism that leverages GPT-2. The model achieved at least a 7% improvement in accuracy over state-of-the-art techniques on TripAdvisor and YelpZip datasets when labeled data was scarce.
Online reviews are a vital source of information when purchasing a service or a product. Opinion spammers manipulate these reviews, deliberately altering the overall perception of the service. Though there exists a corpus of online reviews, only a few have been labeled as spam or non-spam, making it difficult to train spam detection models. We propose an adversarial training mechanism leveraging the capabilities of Generative Pre-Training 2 (GPT-2) for classifying opinion spam with limited labeled data and a large set of unlabeled data. Experiments on TripAdvisor and YelpZip datasets show that the proposed model outperforms state-of-the-art techniques by at least 7% in terms of accuracy when labeled data is limited. The proposed model can also generate synthetic spam/non-spam reviews with reasonable perplexity, thereby, providing additional labeled data during training.